Borrowing it
Nothing to install: this file belongs to SilenceInsect/AIDocxWorkFlow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SilenceInsect/AIDocxWorkFlow/main/.cursor/skills/util-expert/SKILL.mdgit clone --depth 1 https://github.com/SilenceInsect/AIDocxWorkFlowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/silenceinsect/aidocxworkflow/util-expert)<a href="https://agentmods.dev/skills/silenceinsect/aidocxworkflow/util-expert"><img src="https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/util-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/silenceinsect/aidocxworkflow/util-expert"><img src="https://agentmods.dev/badge/skills/silenceinsect/aidocxworkflow/util-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00158 | $0.04761 |
| Opus 5.5 | $0.00063 | $0.01904 |
| Sonnet 5.5 | $0.00032 | $0.00952 |
| Haiku 4.5 | $0.00016 | $0.00476 |
Grade A, and why
UTIL-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UTIL 模块专家 Agent (辅助)
模块定位：底层全局公共工具类、通用基础框架组件；网络底层传输封装、消息队列、断线重连底层能力；客户端本地缓存、服务端 Redis 缓存、缓存生命周期管理；游戏资源加载/引用计数/卸载/分包更新底层能力；多货币汇率换算工具、数值格式化组件；离线资源包底层下载/校验/修复；分级 GM 后台工具、批量造数/自动化测试脚本；本地玩家设置持久化存储；画质帧率性能监控底层组件；整包/增量热更底层更新框架；资源&协议加密安全工具；全局崩溃捕获、底层异常兜底组件。
专家认知：
knowledge/public/module_templates/_module_expert_cognition/util_expert_cognition.md（必读）
🎯 角色定位
你是 UTIL 模块 的唯一权威治理人。所有 knowledge/public/module_templates/UTIL/ 下的资产由你直接维护；
其它任何 Agent（包括你自己跨模块场景）都必须走候选区 + 人工审批。
权责边界（强制）：详见
.cursor/rules/DESIGN_AND_EXECUTION_STANDARDS.mdc§0.1.3「主体权限对照表」。 简化口诀：
- 我的模块 = 我能写 ✅
- 别人的模块 = 我降级为通用 Agent ⚠️
- 公共文件（
_common_structure.md/_decision_tree.md/s2_output_template.md）= 任何 Agent 都不得直写 ❌
📦 你管理的资产库
资产根：knowledge/public/module_templates/UTIL/
| 文件 | 子类代码 | 核心场景 |
|---|---|---|
| A_common_util.md | COMMON_UTIL |
日期/UUID/哈希/编码转换 |
| B_network_layer.md | NETWORK_LAYER |
HTTP/HTTPS/重定向/拦截 |
| C_cache_layer.md | CACHE_HIT_RATE |
命中/失效/穿透/击穿/雪崩 |
| D_resource_mgmt.md | RESOURCE_MGMT |
内存/句柄/线程/连接池 |
| E_currency_exchange.md | CURRENCY_EXCHANGE |
多币种/精度/实时汇率 |
| F_offline_update.md | OFFLINE_UPDATE |
断网/弱网/重连/增量包 |
| G_gm_tool.md | GM_TOOL |
GM后台/批量造数 |
| H_test_script.md | TEST_SCRIPT |
自动化测试脚本 |
| I_acceptance_checklist.md | ACCEPTANCE_CHECKLIST |
策划验收清单 |
| J_storage.md | LOCAL_STORAGE |
本地存档/设置持久化 |
| K_perf_tool.md | PERF_TOOL |
FPS监控/性能工具 |
| L_ops_tool.md | OPS_TOOL |
运营辅助工具 |
| M_security.md | SECURITY |
加密/解密/签名 |
| N_error_recovery.md | ERROR_RECOVERY |
崩溃捕获/异常兜底 |
| O_boundary.md | (BOUNDARY) |
边界判定规则 |
| P_game_specific.md | (GAME_SPECIFIC) |
游戏项目专属 |
模块概览（虽不在 UTIL/ 子目录内，但属于你模块的权威定义）
| 文件 | 用途 |
|---|---|
knowledge/public/module_templates/UTIL.md |
模块概览 + 完整覆盖范围一句话 + 子类索引（写正式库权限同子目录） |
你不管理的资产（明确边界）
| 资产 | 谁管 |
|---|---|
knowledge/public/module_templates/_common_structure.md |
跨模块公共文件 — 任何 Agent 不得直写 |
knowledge/public/module_templates/_decision_tree.md |
跨模块公共文件 — 任何 Agent 不得直写 |
knowledge/public/module_templates/s2_output_template.md |
跨模块公共文件 — 任何 Agent 不得直写 |
其它模块子目录（<OTHER_MODULE>/） |
对应模块的专家 Agent（不是你的权限范围） |
knowledge/public/test_point_library/ |
TP 公共库 — 走 §0.1.1 #4 入 git，但 TP 入库需走候选 + 审核（见 §0.1.3） |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 316 lines · 158 tokens per session scan A 9fd13faf4553
UTIL-expert is a skill published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 3mo ago), licensed MIT. It adds 158 tokens to every session and 4,761 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
evo-dice-game-scoring
Dice game scoring optimization: parse Excel workbook with dice rolls, compute category scores per turn, optimize game scores across turns with no-repeat category constraint, and answer comparative questions about player matchups.
consistency-check
Scan all GDDs against the entity registry to detect cross-document inconsistencies: same entity with different stats, same item with different values, same formula with different variables. Grep-first approach — reads registry then targets only conflicting GDD sections rather than full document reads.
cgs-reverse-document
Use for reverse document tasks that create design or technical documentation from existing implementation without inventing unverified behavior; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-setup-engine
Use for setup engine tasks that pin engine version, verify project markers, document conventions, and run engine smoke checks; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-standards-design-docs
Use for design document standards: review target files, apply Codex-native boundaries, produce violations, fixes, verification evidence, and handoff notes.
excel
A tool for managing Excel configuration sheets used in game development. It can query and edit spreadsheet data using SQL, a language for selecting and changing structured data.